One important property of a preference measure is its reliability. In this article, we explore the reliability of experimental auctions in measuring the market demand for five types of fish. We use the test‐retest method to compare demand curves from two Becker–DeGroot–Marschak experiments with the same 116 participants conducted 7 months apart in time. The individual bids are not stable for these perishable products, but the distributions of the individual bids are stable. We find that the unsystematic individual variations cancel out in the aggregation of bids in a typical sample size for experimental valuation studies. Our results suggest that experimental auctions provide reliable market demand estimates even though the individual bids may change substantially over time.